Articoli di riviste sul tema "Convolutional recurrent neural networks"
Segui questo link per vedere altri tipi di pubblicazioni sul tema: Convolutional recurrent neural networks.
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-50 articoli di riviste per l'attività di ricerca sul tema "Convolutional recurrent neural networks".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi gli articoli di riviste di molte aree scientifiche e compila una bibliografia corretta.
1
Hindarto, Djarot. "Comparison of RNN Architectures and Non-RNN Architectures in Sentiment Analysis". sinkron 8, n. 4 (1 ottobre 2023): 2537–46. http://dx.doi.org/10.33395/sinkron.v8i4.13048.
Abstract (sommario):
This study compares the sentiment analysis performance of multiple Recurrent Neural Network architectures and One-Dimensional Convolutional Neural Networks. THE METHODS EVALUATED ARE simple Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Bidirectional Recurrent Neural Network, and 1D ConvNets. A dataset comprising text reviews with positive or negative sentiment labels was evaluated. All evaluated models demonstrated an extremely high accuracy, ranging from 99.81% to 99.99%. Apart from that, the loss generated by these models is also low, ranging from 0.0043 to 0.0021. However, there are minor performance differences between the evaluated architectures. The Long Short-Term Memory and Gated Recurrent Unit models mainly perform marginally better than the Simple Recurrent Neural Network, albeit with slightly lower accuracy and loss. In the meantime, the Bidirectional Recurrent Neural Network model demonstrates competitive performance, as it can effectively manage text context from both directions. Additionally, One-Dimensional Convolutional Neural Networks provide satisfactory results, indicating that convolution-based approaches are also effective in sentiment analysis. The findings of this study provide practitioners with essential insights for selecting an appropriate architecture for sentiment analysis tasks. While all models yield excellent performance, the choice of architecture can impact computational efficiency and training time. Therefore, a comprehensive comprehension of the respective characteristics of Recurrent Neural Network architectures and One-Dimensional Convolutional Neural Networks is essential for making more informed decisions when constructing sentiment analysis models.
2
Kassylkassova, Kamila, Zhanna Yessengaliyeva, Gayrat Urazboev e Ayman Kassylkassova. "OPTIMIZATION METHOD FOR INTEGRATION OF CONVOLUTIONAL AND RECURRENT NEURAL NETWORK". Eurasian Journal of Mathematical and Computer Applications 11, n. 2 (2023): 40–56. http://dx.doi.org/10.32523/2306-6172-2023-11-2-40-56.
Abstract (sommario):
Abstract In recent years, convolutional neural networks have been widely used in image processing and have shown good results. Particularly useful was their ability to automatically extract image features (textures and shapes of objects). The article proposes a method that improves the accuracy and speed of recognition of an ultra-precise neural network based on image recognition of people’s faces. At first, a recurrent neural network is introduced into the convolutional neural network, thereby studying the characteristics of the image more deeply. Deep image characteristics are studied in parallel using a convolutional and recurrent neural network. In line with the idea of skipping the ResNet convolution layer, a new ShortCut3- ResNet residual module is built. A double optimization model is created to fully optimize the convolution process. A study of the influence of various parameters of a convolutional neural network on network performance is demonstrated, also analyzed using simulation experiments. As a result, the optimal parameters of the convolutional neural network are established. Ex- periments show that the method presented in this paper can study various images of people’s faces regardless of age, gender, and also improves the accuracy of feature extraction and image recognition ability.
3
Lyu, Shengfei, e Jiaqi Liu. "Convolutional Recurrent Neural Networks for Text Classification". Journal of Database Management 32, n. 4 (ottobre 2021): 65–82. http://dx.doi.org/10.4018/jdm.2021100105.
Abstract (sommario):
Recurrent neural network (RNN) and convolutional neural network (CNN) are two prevailing architectures used in text classification. Traditional approaches combine the strengths of these two networks by straightly streamlining them or linking features extracted from them. In this article, a novel approach is proposed to maintain the strengths of RNN and CNN to a great extent. In the proposed approach, a bi-directional RNN encodes each word into forward and backward hidden states. Then, a neural tensor layer is used to fuse bi-directional hidden states to get word representations. Meanwhile, a convolutional neural network is utilized to learn the importance of each word for text classification. Empirical experiments are conducted on several datasets for text classification. The superior performance of the proposed approach confirms its effectiveness.
4
P., Vijay Babu, e Senthil Kumar R. "Performance Evaluation of Brain Tumor Identification and Examination Using MRI Images with Innovative Convolution Neural Networks and Comparing the Accuracy with RNN Algorithm". ECS Transactions 107, n. 1 (24 aprile 2022): 12405–14. http://dx.doi.org/10.1149/10701.12405ecst.
Abstract (sommario):
The main aim of the paper is to find the accuracy for brain tumor detection using the Innovative CNN and RNN algorithms. The paper addresses the design and implementation of brain tumor detection with an accurate prediction. Materials and Methods: Innovative Convolutional Neural Networks and Recurrent Neural Networks are used for finding the accuracy of brain tumor detection. Data models were trained with the neural network algorithms where the brain tumor model adopts the data models and gives responses by adopting those effectively. The model checks patterns for providing the responses to the users by using a pattern matching module. Accuracy calculation was done by using neural network algorithms. Results: The accuracy of Innovative Convolutional Neural Network in brain tumor detection is more significantly improved which is more than 95% (approx.) than the Recurrent Neural Networks. Conclusion: Based on Independent T-test analysis using SPSS statistical software, the innovative Convolutional Neural Network algorithm is significant and has more accuracy compared to Recurrent Neural Networks.
5
Peng, Wenli, Shenglai Zhen, Xin Chen, Qianjing Xiong e Benli Yu. "Study on convolutional recurrent neural networks for speech enhancement in fiber-optic microphones". Journal of Physics: Conference Series 2246, n. 1 (1 aprile 2022): 012084. http://dx.doi.org/10.1088/1742-6596/2246/1/012084.
Abstract (sommario):
Abstract In this paper, several improved convolutional recurrent networks (CRN) are proposed, which can enhance the speech with non-additive distortion captured by fiber-optic microphones. Our preliminary study shows that the original CRN structure based on amplitude spectrum estimation is seriously distorted due to the loss of phase information. Therefore, we transform the network to run in time domain and gain 0.42 improvement on PESQ and 0.03 improvement on STOI. In addition, we integrate dilated convolution into CRN architecture, and adopt three different types of bottleneck modules, namely long short-term memory (LSTM), gated recurrent units (GRU) and dilated convolutions. The experimental results show that the model with dilated convolution in the encoder-decoder and the model with dilated convolution at bottleneck layer have the highest PESQ and STOI scores, respectively.
6
P, Suma, e Senthil Kumar R. "Automatic Classification of Normal and Infected Blood Cells for Leukemia Through Color Based Segmentation Technique Over Innovative CNN Algorithm and Comparing the Error Rate with RNN". ECS Transactions 107, n. 1 (24 aprile 2022): 14123–34. http://dx.doi.org/10.1149/10701.14123ecst.
Abstract (sommario):
To classify the normal infected blood cells through color-based segmentation for leukemia by comparing the error rate for the innovative Convolutional Neural Network and Recurrent Neural Network algorithm. Materials and Methods: Convolutional Neural Network algorithm, which has been taken as an input image and differentiating according to the properties of the image. Here the white blood cells acted as the major parameter for detecting the disease. Result: Data collection was carried out and the analysis could have been done by using blood cell sample images to detect the result and error rate of a particular algorithm. Here in this proposed work, the error rate was reduced in innovative Convolutional Neural Networks compared to Recurrent Neural Networks. Conclusion: The data was collected from various resources for the usage of disease detection. The reduced error rate for the Convolutional Neural Network (87.02%) was used as an algorithm for the whole disease detection process for reduced error rate results compared to the Recurrent Neural Network (89.42%).
7
Wang, Lin, e Zuqiang Meng. "Multichannel Two-Dimensional Convolutional Neural Network Based on Interactive Features and Group Strategy for Chinese Sentiment Analysis". Sensors 22, n. 3 (18 gennaio 2022): 714. http://dx.doi.org/10.3390/s22030714.
Abstract (sommario):
In Chinese sentiment analysis tasks, many existing methods tend to use recurrent neural networks (e.g., long short-term memory networks and gated recurrent units) and standard one-dimensional convolutional neural networks (1D-CNN) to extract features. This is because a recurrent neural network can deal with the order dependence of the data to a certain extent and the one-dimensional convolution can extract local features. Although these methods have good performance in sentiment analysis tasks, recurrent neural networks (RNNs) cannot be parallelized, resulting in time-inefficiency, and the standard 1D-CNN can only extract a single sample feature, with the result that the feature information cannot be fully utilized. To this end, in this paper, we propose a multichannel two-dimensional convolutional neural network based on interactive features and group strategy (MCNN-IFGS) for Chinese sentiment analysis. Firstly, we no longer use word encoding technology but use character-based integer encoding to retain more fine-grained information. Besides, in character-level vectors, the interactive features of different elements are introduced to improve the dimensionality of feature vectors and supplement semantic information so that the input matches the model network. In order to ensure that more sentiment features are learned, group strategies are used to form several feature mapping groups, so the learning object is converted from the traditional single sample to the learning of the feature mapping group, so as to achieve the purpose of learning more features. Finally, multichannel two-dimensional convolutional neural networks with different sizes of convolution kernels are used to extract sentiment features of different scales. The experimental results on the Chinese dataset show that our proposed method outperforms other baseline and state-of-the-art methods.
8
Poudel, Sushan, e Dr R. Anuradha. "Speech Command Recognition using Artificial Neural Networks". JOIV : International Journal on Informatics Visualization 4, n. 2 (26 maggio 2020): 73. http://dx.doi.org/10.30630/joiv.4.2.358.
Abstract (sommario):
Speech is one of the most effective way for human and machine to interact. This project aims to build Speech Command Recognition System that is capable of predicting the predefined speech commands. Dataset provided by Google’s TensorFlow and AIY teams is used to implement different Neural Network models which include Convolutional Neural Network and Recurrent Neural Network combined with Convolutional Neural Network. The combination of Convolutional and Recurrent Neural Network outperforms Convolutional Neural Network alone by 8% and achieved 96.66% accuracy for 20 labels.
9
Wu, Hao, e Saurabh Prasad. "Convolutional Recurrent Neural Networks forHyperspectral Data Classification". Remote Sensing 9, n. 3 (21 marzo 2017): 298. http://dx.doi.org/10.3390/rs9030298.
10
Li, Kezhi, John Daniels, Chengyuan Liu, Pau Herrero e Pantelis Georgiou. "Convolutional Recurrent Neural Networks for Glucose Prediction". IEEE Journal of Biomedical and Health Informatics 24, n. 2 (febbraio 2020): 603–13. http://dx.doi.org/10.1109/jbhi.2019.2908488.
11
Zhang, Zao, e Yuan Dong. "Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data". Complexity 2020 (20 marzo 2020): 1–8. http://dx.doi.org/10.1155/2020/3536572.
Abstract (sommario):
Today, artificial intelligence and deep neural networks have been successfully used in many applications that have fundamentally changed people’s lives in many areas. However, very limited research has been done in the meteorology area, where meteorological forecasts still rely on simulations via extensive computing resources. In this paper, we propose an approach to using the neural network to forecast the future temperature according to the past temperature values. Specifically, we design a convolutional recurrent neural network (CRNN) model that is composed of convolution neural network (CNN) portion and recurrent neural network (RNN) portion. The model can learn the time correlation and space correlation of temperature changes from historical data through neural networks. To evaluate the proposed CRNN model, we use the daily temperature data of mainland China from 1952 to 2018 as training data. The results show that our model can predict future temperature with an error around 0.907°C.
12
Nguyen, Viet-Hung, Minh-Tuan Nguyen, Jeongsik Choi e Yong-Hwa Kim. "NLOS Identification in WLANs Using Deep LSTM with CNN Features". Sensors 18, n. 11 (20 novembre 2018): 4057. http://dx.doi.org/10.3390/s18114057.
Abstract (sommario):
Identifying channel states as line-of-sight or non-line-of-sight helps to optimize location-based services in wireless communications. The received signal strength identification and channel state information are used to estimate channel conditions for orthogonal frequency division multiplexing systems in indoor wireless local area networks. This paper proposes a joint convolutional neural network and recurrent neural network architecture to classify channel conditions. Convolutional neural networks extract the feature from frequency-domain characteristics of channel state information data and recurrent neural networks extract the feature from time-varying characteristics of received signal strength identification and channel state information between packet transmissions. The performance of the proposed methods is verified under indoor propagation environments. Experimental results show that the proposed method has a 2% improvement in classification performance over the conventional recurrent neural network model.
13
Shchetinin, E. Yu. "EMOTIONS RECOGNITION IN HUMAN SPEECH USING DEEP NEURAL NETWORKS". Vestnik komp'iuternykh i informatsionnykh tekhnologii, n. 199 (gennaio 2021): 44–51. http://dx.doi.org/10.14489/vkit.2021.01.pp.044-051.
Abstract (sommario):
The recognition of human emotions is one of the most relevant and dynamically developing areas of modern speech technologies, and the recognition of emotions in speech (RER) is the most demanded part of them. In this paper, we propose a computer model of emotion recognition based on an ensemble of bidirectional recurrent neural network with LSTM memory cell and deep convolutional neural network ResNet18. In this paper, computer studies of the RAVDESS database containing emotional speech of a person are carried out. RAVDESS-a data set containing 7356 files. Entries contain the following emotions: 0 – neutral, 1 – calm, 2 – happiness, 3 – sadness, 4 – anger, 5 – fear, 6 – disgust, 7 – surprise. In total, the database contains 16 classes (8 emotions divided into male and female) for a total of 1440 samples (speech only). To train machine learning algorithms and deep neural networks to recognize emotions, existing audio recordings must be pre-processed in such a way as to extract the main characteristic features of certain emotions. This was done using Mel-frequency cepstral coefficients, chroma coefficients, as well as the characteristics of the frequency spectrum of audio recordings. In this paper, computer studies of various models of neural networks for emotion recognition are carried out on the example of the data described above. In addition, machine learning algorithms were used for comparative analysis. Thus, the following models were trained during the experiments: logistic regression (LR), classifier based on the support vector machine (SVM), decision tree (DT), random forest (RF), gradient boosting over trees – XGBoost, convolutional neural network CNN, recurrent neural network RNN (ResNet18), as well as an ensemble of convolutional and recurrent networks Stacked CNN-RNN. The results show that neural networks showed much higher accuracy in recognizing and classifying emotions than the machine learning algorithms used. Of the three neural network models presented, the CNN + BLSTM ensemble showed higher accuracy.
14
Hou, Kai. "Principal Component Analysis and Prediction of Students’ Physical Health Standard Test Results Based on Recurrent Convolution Neural Network". Wireless Communications and Mobile Computing 2021 (4 settembre 2021): 1–11. http://dx.doi.org/10.1155/2021/2438656.
Abstract (sommario):
The recurrent convolutional neural network is an advanced neural network that integrates deep structure and convolution calculation. The feedforward neural network with convolution operation and deep structure is an important method of deep learning. In this paper, the convolutional neural network and the recurrent neural network are combined to establish a recurrent convolutional neural network model composed of anomalies, LSTM (Long Short-Term Memory), and CNN. This study combines the principal component analysis method to predict and analyze the test results of students’ physical fitness standards. The innovation lies in the introduction of the function of the recurrent convolutional network and the use of principal component analysis to conduct qualitative research on seven evaluation indicators that reflect the three aspects of students’ physical health. The results of the study clearly show that there is a strong correlation between some indicators, such as standing long jump and sitting bends which may have a strong correlation. The first principal component eigenvalue has the highest contribution rate, which mainly reflects the five indicators of standing long jump, sitting forward bend, pull-up, 50 m sprint, and 1000 m long-distance running. This shows that the physical fitness indicators have a great impact on the physical health of students, which also reflects the current status of students’ physical fitness problems. The results of principal component analysis are scientific and reasonable.
15
D, Sreekanth. "Metro Water Fraudulent Prediction in Houses Using Convolutional Neural Network and Recurrent Neural Network". Revista Gestão Inovação e Tecnologias 11, n. 4 (10 luglio 2021): 1177–87. http://dx.doi.org/10.47059/revistageintec.v11i4.2177.
16
Ma, Hao, Chao Chen, Qing Zhu, Haitao Yuan, Liming Chen e Minglei Shu. "An ECG Signal Classification Method Based on Dilated Causal Convolution". Computational and Mathematical Methods in Medicine 2021 (2 febbraio 2021): 1–10. http://dx.doi.org/10.1155/2021/6627939.
Abstract (sommario):
The incidence of cardiovascular disease is increasing year by year and is showing a younger trend. At the same time, existing medical resources are tight. The automatic detection of ECG signals becomes increasingly necessary. This paper proposes an automatic classification of ECG signals based on a dilated causal convolutional neural network. To solve the problem that the recurrent neural network framework network cannot be accelerated by hardware equipment, the dilated causal convolutional neural network is adopted. Given the features of the same input and output time steps of the recurrent neural network and the nondisclosure of future information, the network is constructed with fully convolutional networks and causal convolution. To reduce the network depth and prevent gradient explosion or gradient disappearance, the dilated factor is introduced into the model, and the residual blocks are introduced into the model according to the shortcut connection idea. The effectiveness of the algorithm is verified in the MIT-BIH Atrial Fibrillation Database (MIT-BIH AFDB). In the experiment of the MIT-BIH AFDB database, the classification accuracy rate is 98.65%.
17
R, Gayathri, Lydia Beryl D, Gowtham M, Naveen Kumar N e Dr M. S. Anbarasi. "Detection and Classification of Cyberbullying Using CR*". International Journal for Research in Applied Science and Engineering Technology 11, n. 4 (30 aprile 2023): 24–29. http://dx.doi.org/10.22214/ijraset.2023.49984.
Abstract (sommario):
Abstract: Cyberbullying is one of the latest threats in the online world, affecting millions of people worldwide. The detection of cyberbullying became a challenging task due to the complexity involved. In this paper, we propose a novel approach for cyberbullying detection using CR* which concatenates the deep learning model’s features such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) which helps in detecting text, audio, and emoji. Initially, we collect a dataset of cyberbullying messages from social media platforms. Then we integrate convolutional neural networks and recurrent neural networks to build our deep learning model entitled Convolutional Recurrent (CR*) to extract features from a combination of the text data, emoji, and audio. The multimodal features were then concatenated and passed through fully connected layers for classification. The proposed approach can be useful for detecting cyberbullying on various online platforms and can help prevent the spread of cyberbullying.
18
Guo, Yanbu, Bingyi Wang, Weihua Li e Bei Yang. "Protein secondary structure prediction improved by recurrent neural networks integrated with two-dimensional convolutional neural networks". Journal of Bioinformatics and Computational Biology 16, n. 05 (ottobre 2018): 1850021. http://dx.doi.org/10.1142/s021972001850021x.
Abstract (sommario):
Protein secondary structure prediction (PSSP) is an important research field in bioinformatics. The representation of protein sequence features could be treated as a matrix, which includes the amino-acid residue (time-step) dimension and the feature vector dimension. Common approaches to predict secondary structures only focus on the amino-acid residue dimension. However, the feature vector dimension may also contain useful information for PSSP. To integrate the information on both dimensions of the matrix, we propose a hybrid deep learning framework, two-dimensional convolutional bidirectional recurrent neural network (2C-BRNN), for improving the accuracy of 8-class secondary structure prediction. The proposed hybrid framework is to extract the discriminative local interactions between amino-acid residues by two-dimensional convolutional neural networks (2DCNNs), and then further capture long-range interactions between amino-acid residues by bidirectional gated recurrent units (BGRUs) or bidirectional long short-term memory (BLSTM). Specifically, our proposed 2C-BRNNs framework consists of four models: 2DConv-BGRUs, 2DCNN-BGRUs, 2DConv-BLSTM and 2DCNN-BLSTM. Among these four models, the 2DConv- models only contain two-dimensional (2D) convolution operations. Moreover, the 2DCNN- models contain 2D convolutional and pooling operations. Experiments are conducted on four public datasets. The experimental results show that our proposed 2DConv-BLSTM model performs significantly better than the benchmark models. Furthermore, the experiments also demonstrate that the proposed models can extract more meaningful features from the matrix of proteins, and the feature vector dimension is also useful for PSSP. The codes and datasets of our proposed methods are available at https://github.com/guoyanb/JBCB2018/ .
19
Pan, Yumin. "Different Types of Neural Networks and Applications: Evidence from Feedforward, Convolutional and Recurrent Neural Networks". Highlights in Science, Engineering and Technology 85 (13 marzo 2024): 247–55. http://dx.doi.org/10.54097/6rn1wd81.
Abstract (sommario):
Neural networks have achieved great process in the 90 years since they were officially introduced in 1943. Because of its wide application and huge research and development potential, this technology attracts more and more scientific and technological workers to the research of neural networks. Neural network technology is an essential component of AI development, and it is a significant indicator of a country's overall strength. In this paper, this study will demonstrate Feedforward Neural Network, Convolution Neural Network and Recurrent Neural networks and evaluate them through datasets from kaggle.com. and CSDN (China IT community). Through this paper, readers can have a better outlook and understanding of the operating principles of each type of neural network as well as their specific jobs (what kind of jobs they specialized in) and each application of these neural networks. So that this paper can promote readers' thoughts and help them start learning neural networks or be a supplement or reference for future scholars. In the end, this paper will present the outcome, which is the evaluation of the accuracy, loss curve, and accuracy curve of neural networks.
20
Z, Farhan, Kavipriya A, Abinaya C e Ezhilarasan M. "Enhanced Image Segmentation Using Convolutional Recurrent Neural Networks". International Innovative Research Journal of Engineering and Technology 5, n. 3 (30 marzo 2020): 78–83. http://dx.doi.org/10.32595/iirjet.org/v5i3.2020.118.
21
Albaqshi, Hussain, e Alaa Sagheer. "Dysarthric Speech Recognition using Convolutional Recurrent Neural Networks". International Journal of Intelligent Engineering and Systems 13, n. 6 (31 dicembre 2020): 384–92. http://dx.doi.org/10.22266/ijies2020.1231.34.
Abstract (sommario):
Automatic speech recognition (ASR) transcribes the human voice into a text automatically. Recently, ASR systems has reached, almost, the human performance in specific scenarios. In contrast, dysarthric speech recognition (DSR) is still a challenging task due to many reasons including unintelligible speech, irregular phonemes articulation, along with scarcity and heterogeneous of data. Most of the existing DSR works are employed the ASR systems that trained on an unimpaired speech to recognize such impaired speech, which of course is impractical and inefficient. In this paper, we developed a deep architecture of the convolutional recurrent neural network (CRNN) model and compared its performance with the vanilla convolutional neural network (CNN) model. We train both models using the samples of the Torgo dataset, which contains a mixed of impaired and unimpaired speech data. The experimental results show that the CRNN model attains 40.6% against 31.4% for the vanilla CNN. This indicates the effectiveness of the proposed hybrid structure of the CRNN to improve the recognition of dysarthric speech.
22
Santacroce, Michael, Daniel Koranek e Rashmi Jha. "Detecting Malicious Assembly using Convolutional, Recurrent Neural Networks". Advances in Science, Technology and Engineering Systems Journal 4, n. 5 (2019): 46–52. http://dx.doi.org/10.25046/aj040506.
23
Gayathri, P., P. Gowri Priya, L. Sravani, Sandra Johnson e Visanth Sampath. "Convolutional Recurrent Neural Networks Based Speech Emotion Recognition". Journal of Computational and Theoretical Nanoscience 17, n. 8 (1 agosto 2020): 3786–89. http://dx.doi.org/10.1166/jctn.2020.9321.
Abstract (sommario):
Recognition of emotions is the aspect of speech recognition that is gaining more attention and the need for it is growing enormously. Although there are methods to identify emotion using machine learning techniques, we assume in this paper that calculating deltas and delta-deltas for customized features not only preserves effective emotional information, but also that the impact of irrelevant emotional factors, leading to a reduction in misclassification. Furthermore, Speech Emotion Recognition (SER) often suffers from the silent frames and irrelevant emotional frames. Meanwhile, the process of attention has demonstrated exceptional performance in learning related feature representations for specific tasks. Inspired by this, propose a Convolutionary Recurrent Neural Networks (ACRNN) based on Attention to learn discriminative features for SER, where the Mel-spectrogram with deltas and delta-deltas is used as input. Finally, experimental results show the feasibility of the proposed method and attain state-of-the-art performance in terms of unweighted average recall.
24
Hu, Wenjin, Jiawei Xiong, Ning Wang, Feng Liu, Yao Kong e Chaozhong Yang. "Integrated Model Text Classification Based on Multineural Networks". Electronics 13, n. 2 (22 gennaio 2024): 453. http://dx.doi.org/10.3390/electronics13020453.
Abstract (sommario):
Based on the original deep network architecture, this paper replaces the deep integrated network by integrating shallow FastText, a bidirectional gated recurrent unit (GRU) network and the convolutional neural networks (CNNs). In FastText, word embedding, 2-grams and 3-grams are combined to extract text features. In recurrent neural networks (RNNs), a bidirectional GRU network is used to lessen information loss during the process of transmission. In CNNs, text features are extracted using various convolutional kernel sizes. Additionally, three optimization algorithms are utilized to improve the classification capabilities of each network architecture. The experimental findings using the social network news dataset demonstrate that the integrated model is effective in improving the accuracy of text classification.
25
Huang, Feizhen, Jinfang Zeng, Yu Zhang e Wentao Xu. "Convolutional recurrent neural networks with multi-sized convolution filters for sound-event recognition". Modern Physics Letters B 34, n. 23 (25 aprile 2020): 2050235. http://dx.doi.org/10.1142/s0217984920502358.
Abstract (sommario):
Sound-event recognition often utilizes time-frequency analysis to produce an image-like spectrogram that provides a rich visual representation of original signal in time and frequency. Convolutional Neural Networks (CNN) with the ability of learning discriminative spectrogram patterns are suitable for sound-event recognition. However, there is relatively little effort that CNN makes full use of the important temporal information. In this paper, we propose MCRNN, a Convolutional Recurrent Neural Networks (CRNN) architecture for sound-event recognition, the letter “M” in the name “MCRNN” of our model denotes the multi-sized convolution filters. Richer features are extracted by using several different convolution filter sizes at the last convolution layer. In addition, cochleagram images are used as the input layer of the network, instead of the traditional spectrogram image of a sound signal. Experiments on the RWCP dataset shows that the recognition rate of the proposed method achieved 98.4% in clean conditions, and it robustly outperforms the existing methods, the recognition rate increased by 0.9%, 1.9% and 10.3% in 20 dB, 10 dB and 0 dB signal-to-noise ratios (SNR), respectively.
26
Kim, Deageon. "Research On Text Classification Based On Deep Neural Network". International Journal of Communication Networks and Information Security (IJCNIS) 14, n. 1s (31 dicembre 2022): 100–113. http://dx.doi.org/10.17762/ijcnis.v14i1s.5618.
Abstract (sommario):
Text classification is one of the classic tasks in the field of natural language processing. The goal is to identify the category to which the text belongs. Text categorization is widely used in email detection, sentiment analysis, topic marking and other fields. However, good text representation is the key to improve the performance of natural language processing tasks such as text classification. Traditional text representation adopts bag-of-words model or vector space model, which not only loses the context information of the text, but also faces the problems of high latitude and high sparsity. In recent years, with the increase of data and the improvement of computing performance, the use of deep learning technology to represent and classify texts has attracted great attention. Convolutional neural network, recurrent neural network and recurrent neural network with attention mechanism are used to represent the text, and then to classify the text and other natural language processing tasks, all of which have better performance than the traditional methods. In this paper, we design two sentence-level text representation and classification models based on the deep network. The details are as follows: (1) Text representation and classification model based on bidirectional cyclic and convolutional neural networks-BRCNN. Brcnn's input is the word vector corresponding to each word in the sentence; After using cyclic neural network to extract word order information in sentences, convolution neural network is used to extract higher-level features of sentences. After convolution, the maximum pool operation is used to obtain sentence vectors. At last, softmax classifier is used for classification. Cyclic neural network can capture the word order information in sentences, while convolutional neural network can extract useful features. Experiments on eight text classification tasks show that BRCNN model can get better text feature representation, and the classification accuracy rate is equal to or higher than that of the prior art.. (2) A text representation and classification model based on attention mechanism and convolutional neural network-ACNN. ACNN model uses the recurrent neural network with attention mechanism to obtain the context vector; Then convolution neural network is used to extract more advanced feature information. The maximum pool operation is adopted to obtain a sentence vector; At last, the softmax classifier is used to classify the text. Experiments on eight text classification benchmark data sets show that ACNN improves the stability of model convergence, and can converge to an optimal or local optimal solution better than BRCNN.
27
Khan, Muhammad Ashfaq. "HCRNNIDS: Hybrid Convolutional Recurrent Neural Network-Based Network Intrusion Detection System". Processes 9, n. 5 (10 maggio 2021): 834. http://dx.doi.org/10.3390/pr9050834.
Abstract (sommario):
Nowadays, network attacks are the most crucial problem of modern society. All networks, from small to large, are vulnerable to network threats. An intrusion detection (ID) system is critical for mitigating and identifying malicious threats in networks. Currently, deep learning (DL) and machine learning (ML) are being applied in different domains, especially information security, for developing effective ID systems. These ID systems are capable of detecting malicious threats automatically and on time. However, malicious threats are occurring and changing continuously, so the network requires a very advanced security solution. Thus, creating an effective and smart ID system is a massive research problem. Various ID datasets are publicly available for ID research. Due to the complex nature of malicious attacks with a constantly changing attack detection mechanism, publicly existing ID datasets must be modified systematically on a regular basis. So, in this paper, a convolutional recurrent neural network (CRNN) is used to create a DL-based hybrid ID framework that predicts and classifies malicious cyberattacks in the network. In the HCRNNIDS, the convolutional neural network (CNN) performs convolution to capture local features, and the recurrent neural network (RNN) captures temporal features to improve the ID system’s performance and prediction. To assess the efficacy of the hybrid convolutional recurrent neural network intrusion detection system (HCRNNIDS), experiments were done on publicly available ID data, specifically the modern and realistic CSE-CIC-DS2018 data. The simulation outcomes prove that the proposed HCRNNIDS substantially outperforms current ID methodologies, attaining a high malicious attack detection rate accuracy of up to 97.75% for CSE-CIC-IDS2018 data with 10-fold cross-validation.
28
Solovyeva, Elena, e Ali Abdullah. "Binary and Multiclass Text Classification by Means of Separable Convolutional Neural Network". Inventions 6, n. 4 (19 ottobre 2021): 70. http://dx.doi.org/10.3390/inventions6040070.
Abstract (sommario):
In this paper, the structure of a separable convolutional neural network that consists of an embedding layer, separable convolutional layers, convolutional layer and global average pooling is represented for binary and multiclass text classifications. The advantage of the proposed structure is the absence of multiple fully connected layers, which is used to increase the classification accuracy but raises the computational cost. The combination of low-cost separable convolutional layers and a convolutional layer is proposed to gain high accuracy and, simultaneously, to reduce the complexity of neural classifiers. Advantages are demonstrated at binary and multiclass classifications of written texts by means of the proposed networks under the sigmoid and Softmax activation functions in convolutional layer. At binary and multiclass classifications, the accuracy obtained by separable convolutional neural networks is higher in comparison with some investigated types of recurrent neural networks and fully connected networks.
29
Rymarczyk, T., D. Wójcik, Ł. Maciura, W. Rosa e M. Bartosik. "Body surface potential mapping time series recognition using convolutional and recurrent neural networks". Journal of Physics: Conference Series 2408, n. 1 (1 dicembre 2022): 012001. http://dx.doi.org/10.1088/1742-6596/2408/1/012001.
Abstract (sommario):
Abstract This article shows recognition of biomedical time series from Body Surface Potential Mapping by means of different convolutional and recurrent neural networks models. The various kinds of neural networks models were examined and compared: model with 1D convolutional layer, model with Long - Short Term Memory layer and model with Gated Recurrent Unit layer.
30
Wan, Renzhuo, Shuping Mei, Jun Wang, Min Liu e Fan Yang. "Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting". Electronics 8, n. 8 (7 agosto 2019): 876. http://dx.doi.org/10.3390/electronics8080876.
Abstract (sommario):
Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.
31
Casabianca, Pietro, e Yu Zhang. "Acoustic-Based UAV Detection Using Late Fusion of Deep Neural Networks". Drones 5, n. 3 (26 giugno 2021): 54. http://dx.doi.org/10.3390/drones5030054.
Abstract (sommario):
Multirotor UAVs have become ubiquitous in commercial and public use. As they become more affordable and more available, the associated security risks further increase, especially in relation to airspace breaches and the danger of drone-to-aircraft collisions. Thus, robust systems must be set in place to detect and deal with hostile drones. This paper investigates the use of deep learning methods to detect UAVs using acoustic signals. Deep neural network models are trained with mel-spectrograms as inputs. In this case, Convolutional Neural Networks (CNNs) are shown to be the better performing network, compared with Recurrent Neural Networks (RNNs) and Convolutional Recurrent Neural Networks (CRNNs). Furthermore, late fusion methods have been evaluated using an ensemble of deep neural networks, where the weighted soft voting mechanism has achieved the highest average accuracy of 94.7%, which has outperformed the solo models. In future work, the developed late fusion technique could be utilized with radar and visual methods to further improve the UAV detection performance.
32
Xu, Zhijing, Yuhao Huo, Kun Liu e Sidong Liu. "Detection of ship targets in photoelectric images based on an improved recurrent attention convolutional neural network". International Journal of Distributed Sensor Networks 16, n. 3 (marzo 2020): 155014772091295. http://dx.doi.org/10.1177/1550147720912959.
Abstract (sommario):
Deep learning algorithms have been increasingly used in ship image detection and classification. To improve the ship detection and classification in photoelectric images, an improved recurrent attention convolutional neural network is proposed. The proposed network has a multi-scale architecture and consists of three cascading sub-networks, each with a VGG19 network for image feature extraction and an attention proposal network for locating feature area. A scale-dependent pooling algorithm is designed to select an appropriate convolution in the VGG19 network for classification, and a multi-feature mechanism is introduced in attention proposal network to describe the feature regions. The VGG19 and attention proposal network are cross-trained to accelerate convergence and to improve detection accuracy. The proposed method is trained and validated on a self-built ship database and effectively improve the detection accuracy to 86.7% outperforming the baseline VGG19 and recurrent attention convolutional neural network methods.
33
Liu, Xuanxin, Fu Xu, Yu Sun, Haiyan Zhang e Zhibo Chen. "Convolutional Recurrent Neural Networks for Observation-Centered Plant Identification". Journal of Electrical and Computer Engineering 2018 (2018): 1–7. http://dx.doi.org/10.1155/2018/9373210.
Abstract (sommario):
Traditional image-centered methods of plant identification could be confused due to various views, uneven illuminations, and growth cycles. To tolerate the significant intraclass variances, the convolutional recurrent neural networks (C-RNNs) are proposed for observation-centered plant identification to mimic human behaviors. The C-RNN model is composed of two components: the convolutional neural network (CNN) backbone is used as a feature extractor for images, and the recurrent neural network (RNN) units are built to synthesize multiview features from each image for final prediction. Extensive experiments are conducted to explore the best combination of CNN and RNN. All models are trained end-to-end with 1 to 3 plant images of the same observation by truncated back propagation through time. The experiments demonstrate that the combination of MobileNet and Gated Recurrent Unit (GRU) is the best trade-off of classification accuracy and computational overhead on the Flavia dataset. On the holdout test set, the mean 10-fold accuracy with 1, 2, and 3 input leaves reached 99.53%, 100.00%, and 100.00%, respectively. On the BJFU100 dataset, the C-RNN model achieves the classification rate of 99.65% by two-stage end-to-end training. The observation-centered method based on the C-RNNs shows potential to further improve plant identification accuracy.
34
Kwak, Jin-Yeol, e Yong-Joo Chung. "Sound Event Detection Using Derivative Features in Deep Neural Networks". Applied Sciences 10, n. 14 (17 luglio 2020): 4911. http://dx.doi.org/10.3390/app10144911.
Abstract (sommario):
We propose using derivative features for sound event detection based on deep neural networks. As input to the networks, we used log-mel-filterbank and its first and second derivative features for each frame of the audio signal. Two deep neural networks were used to evaluate the effectiveness of these derivative features. Specifically, a convolutional recurrent neural network (CRNN) was constructed by combining a convolutional neural network and a recurrent neural networks (RNN) followed by a feed-forward neural network (FNN) acting as a classification layer. In addition, a mean-teacher model based on an attention CRNN was used. Both models had an average pooling layer at the output so that weakly labeled and unlabeled audio data may be used during model training. Under the various training conditions, depending on the neural network architecture and training set, the use of derivative features resulted in a consistent performance improvement by using the derivative features. Experiments on audio data from the Detection and Classification of Acoustic Scenes and Events 2018 and 2019 challenges indicated that a maximum relative improvement of 16.9% was obtained in terms of the F-score.
35
Wang, Weiping, Feng Zhang, Xi Luo e Shigeng Zhang. "PDRCNN: Precise Phishing Detection with Recurrent Convolutional Neural Networks". Security and Communication Networks 2019 (29 ottobre 2019): 1–15. http://dx.doi.org/10.1155/2019/2595794.
Abstract (sommario):
Through well-designed counterfeit websites, phishing induces online users to visit forged web pages to obtain their private sensitive information, e.g., account number and password. Existing antiphishing approaches are mostly based on page-related features, which require to crawl content of web pages as well as accessing third-party search engines or DNS services. This not only leads to their low efficiency in detecting phishing but also makes them rely on network environment and third-party services heavily. In this paper, we propose a fast phishing website detection approach called PDRCNN that relies only on the URL of the website. PDRCNN neither needs to retrieve content of the target website nor uses any third-party services as previous approaches do. It encodes the information of an URL into a two-dimensional tensor and feeds the tensor into a novelly designed deep learning neural network to classify the original URL. We first use a bidirectional LSTM network to extract global features of the constructed tensor and give all string information to each character in the URL. After that, we use a CNN to automatically judge which characters play key roles in phishing detection, capture the key components of the URL, and compress the extracted features into a fixed length vector space. By combining the two types of networks, PDRCNN achieves better performance than just using either one of them. We built a dataset containing nearly 500,000 URLs which are obtained through Alexa and PhishTank. Experimental results show that PDRCNN achieves a detection accuracy of 97% and an AUC value of 99%, which is much better than state-of-the-art approaches. Furthermore, the recognition process is very fast: on the trained PDRCNN model, the average per URL detection time only cost 0.4 ms.
36
Chen, Jingwen, Yingwei Pan, Yehao Li, Ting Yao, Hongyang Chao e Tao Mei. "Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning". Proceedings of the AAAI Conference on Artificial Intelligence 33 (17 luglio 2019): 8167–74. http://dx.doi.org/10.1609/aaai.v33i01.33018167.
Abstract (sommario):
It is well believed that video captioning is a fundamental but challenging task in both computer vision and artificial intelligence fields. The prevalent approach is to map an input video to a variable-length output sentence in a sequence to sequence manner via Recurrent Neural Network (RNN). Nevertheless, the training of RNN still suffers to some degree from vanishing/exploding gradient problem, making the optimization difficult. Moreover, the inherently recurrent dependency in RNN prevents parallelization within a sequence during training and therefore limits the computations. In this paper, we present a novel design — Temporal Deformable Convolutional Encoder-Decoder Networks (dubbed as TDConvED) that fully employ convolutions in both encoder and decoder networks for video captioning. Technically, we exploit convolutional block structures that compute intermediate states of a fixed number of inputs and stack several blocks to capture long-term relationships. The structure in encoder is further equipped with temporal deformable convolution to enable free-form deformation of temporal sampling. Our model also capitalizes on temporal attention mechanism for sentence generation. Extensive experiments are conducted on both MSVD and MSR-VTT video captioning datasets, and superior results are reported when comparing to conventional RNN-based encoder-decoder techniques. More remarkably, TDConvED increases CIDEr-D performance from 58.8% to 67.2% on MSVD.
37
Liang, Kaiwei, Na Qin, Deqing Huang e Yuanzhe Fu. "Convolutional Recurrent Neural Network for Fault Diagnosis of High-Speed Train Bogie". Complexity 2018 (23 ottobre 2018): 1–13. http://dx.doi.org/10.1155/2018/4501952.
Abstract (sommario):
Timely detection and efficient recognition of fault are challenging for the bogie of high-speed train (HST), owing to the fact that different types of fault signals have similar characteristics in the same frequency range. Notice that convolutional neural networks (CNNs) are powerful in extracting high-level local features and that recurrent neural networks (RNNs) are capable of learning long-term context dependencies in vibration signals. In this paper, by combining CNN and RNN, a so-called convolutional recurrent neural network (CRNN) is proposed to diagnose various faults of the HST bogie, where the capabilities of CNN and RNN are inherited simultaneously. Within the novel architecture, the proposed CRNN first filters out the features from the original data through convolutional layers. Then, four recurrent layers with simple recurrent cell are used to model the context information in the extracted features. By comparing the performance of the presented CRNN with CNN, RNN, and ensemble learning, experimental results show that CRNN achieves not only the best performance with accuracy of 97.8% but also the least time spent in training model.
38
Wang, Guanchao. "Analysis of sentiment analysis model based on deep learning". Applied and Computational Engineering 5, n. 1 (14 giugno 2023): 750–56. http://dx.doi.org/10.54254/2755-2721/5/20230694.
Abstract (sommario):
A traditional yet important topic in the study of natural language processing is sentiment analysis. Deep learning models have gradually taken over as one of the primary techniques for resolving sentiment analysis issues over the last ten years. Common deep learning models targeting sentiment analysis tasks include both recurrent and convolutional neural networks, as well as the BERT model. The current research examines the classificational accuracy of numerous deep learning models with diverse structural types in order to compare their performance in sentiment analysis. Results from the experiments suggest that the pre-training BERT model achieves the highest accuracy, while the convolutional neural network appears to sustain better results on sentiment analysis than standard recurrent neural networks.
39
Yüksel, Kıvanç, e Władysław Skarbek. "Convolutional and Recurrent Neural Networks for Face Image Analysis". Foundations of Computing and Decision Sciences 44, n. 3 (1 settembre 2019): 331–47. http://dx.doi.org/10.2478/fcds-2019-0017.
Abstract (sommario):
Abstract In the presented research two Deep Neural Network (DNN) models for face image analysis were developed. The first one detects eyes, nose and mouth and it is based on a moderate size Convolutional Neural Network (CNN) while the second one identifies 68 landmarks resulting in a novel Face Alignment Network composed of a CNN and a recurrent neural network. The Face Parts Detector inputs face image and outputs the pixel coordinates of bounding boxes for detected facial parts. The Face Alignment Network extracts deep features in CNN module while in the recurrent module it generates 68 facial landmarks using not only this deep features, but also the geometry of facial parts. Both methods are robust to varying head poses and changing light conditions.
40
Liu, Nan. "Study on the Application of Improved Audio Recognition Technology Based on Deep Learning in Vocal Music Teaching". Mathematical Problems in Engineering 2022 (18 agosto 2022): 1–12. http://dx.doi.org/10.1155/2022/1002105.
Abstract (sommario):
As one of the hotspots in music information extraction research, music recognition has received extensive attention from scholars in recent years. Most of the current research methods are based on traditional signal processing methods, and there is still a lot of room for improvement in recognition accuracy and recognition efficiency. There are few research studies on music recognition based on deep neural networks. This paper expounds on the basic principles of deep learning and the basic structure and training methods of neural networks. For two kinds of commonly used deep networks, convolutional neural network and recurrent neural network, their typical structures, training methods, advantages, and disadvantages are analyzed. At the same time, a variety of platforms and tools for training deep neural networks are introduced, and their advantages and disadvantages are compared. TensorFlow and Keras frameworks are selected from them, and the practice related to neural network research is carried out. Training lays the foundation. Results show that through the development and experimental demonstration of the prototype system, as well as the comparison with other researchers in the field of humming recognition, it is proved that the deep-learning method can be applied to the humming recognition problem, which can effectively improve the accuracy of humming recognition and improve the recognition time. A convolutional recurrent neural network is designed and implemented, combining the local feature extraction of the convolutional layer and the ability of the recurrent layer to summarize the sequence features, to learn the features of the humming signal, so as to obtain audio features with a higher degree of abstraction and complexity and improve the performance of the humming signal. The ability of neural networks to learn the features of audio signals lays the foundation for an efficient and accurate humming recognition process.
41
Le, Viet-Tuan, Kiet Tran-Trung e Vinh Truong Hoang. "A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition". Computational Intelligence and Neuroscience 2022 (20 aprile 2022): 1–17. http://dx.doi.org/10.1155/2022/8323962.
Abstract (sommario):
Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey.
42
Cheng, Yepeng, Zuren Liu e Yasuhiko Morimoto. "Attention-Based SeriesNet: An Attention-Based Hybrid Neural Network Model for Conditional Time Series Forecasting". Information 11, n. 6 (5 giugno 2020): 305. http://dx.doi.org/10.3390/info11060305.
Abstract (sommario):
Traditional time series forecasting techniques can not extract good enough sequence data features, and their accuracies are limited. The deep learning structure SeriesNet is an advanced method, which adopts hybrid neural networks, including dilated causal convolutional neural network (DC-CNN) and Long-short term memory recurrent neural network (LSTM-RNN), to learn multi-range and multi-level features from multi-conditional time series with higher accuracy. However, they didn’t consider the attention mechanisms to learn temporal features. Besides, the conditioning method for CNN and RNN is not specific, and the number of parameters in each layer is tremendous. This paper proposes the conditioning method for two types of neural networks, and respectively uses the gated recurrent unit network (GRU) and the dilated depthwise separable temporal convolutional networks (DDSTCNs) instead of LSTM and DC-CNN for reducing the parameters. Furthermore, this paper presents the lightweight RNN-based hidden state attention module (HSAM) combined with the proposed CNN-based convolutional block attention module (CBAM) for time series forecasting. Experimental results show our model is superior to other models from the viewpoint of forecasting accuracy and computation efficiency.
43
Fantaye, Tessfu Geteye, Junqing Yu e Tulu Tilahun Hailu. "Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition". Computers 9, n. 2 (2 maggio 2020): 36. http://dx.doi.org/10.3390/computers9020036.
Abstract (sommario):
Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recognition task. Of these networks, convolutional neural network (CNN) is an effective network for representing the local properties of the speech formants. However, CNN is not suitable for modeling the long-term context dependencies between speech signal frames. Recently, the recurrent neural networks (RNNs) have shown great abilities for modeling long-term context dependencies. However, the performance of RNNs is not good for low-resource speech recognition tasks, and is even worse than the conventional feed-forward neural networks. Moreover, these networks often overfit severely on the training corpus in the low-resource speech recognition tasks. This paper presents the results of our contributions to combine CNN and conventional RNN with gate, highway, and residual networks to reduce the above problems. The optimal neural network structures and training strategies for the proposed neural network models are explored. Experiments were conducted on the Amharic and Chaha datasets, as well as on the limited language packages (10-h) of the benchmark datasets released under the Intelligence Advanced Research Projects Activity (IARPA) Babel Program. The proposed neural network models achieve 0.1–42.79% relative performance improvements over their corresponding feed-forward DNN, CNN, bidirectional RNN (BRNN), or bidirectional gated recurrent unit (BGRU) baselines across six language collections. These approaches are promising candidates for developing better performance acoustic models for low-resource speech recognition tasks.
44
Zhao, Ping, Zhijie Fan*, Zhiwei Cao e Xin Li. "Intrusion Detection Model Using Temporal Convolutional Network Blend Into Attention Mechanism". International Journal of Information Security and Privacy 16, n. 1 (gennaio 2022): 1–20. http://dx.doi.org/10.4018/ijisp.290832.
Abstract (sommario):
In order to improve the ability to detect network attacks, traditional intrusion detection models often used convolutional neural networks to encode spatial information or recurrent neural networks to obtain temporal features of the data. Some models combined the two methods to extract spatio-temporal features. However, these approaches used separate models and learned features insufficiently. This paper presented an improved model based on temporal convolutional networks (TCN) and attention mechanism. The causal and dilation convolution can capture the spatio-temporal dependencies of the data. The residual blocks allow the network to transfer information in a cross-layered manner, enabling in-depth network learning. Meanwhile, attention mechanism can enhance the model's attention to the relevant anomalous features of different attacks. Finally, this paper compared models results on the KDD CUP99 and UNSW-NB15 datasets. Besides, the authors apply the model to video surveillance network attack detection scenarios. The result shows that the model has advantages in evaluation metrics.
45
Fabien-Ouellet, Gabriel, e Rahul Sarkar. "Seismic velocity estimation: A deep recurrent neural-network approach". GEOPHYSICS 85, n. 1 (19 dicembre 2019): U21—U29. http://dx.doi.org/10.1190/geo2018-0786.1.
Abstract (sommario):
Applying deep learning to 3D velocity model building remains a challenge due to the sheer volume of data required to train large-scale artificial neural networks. Moreover, little is known about what types of network architectures are appropriate for such a complex task. To ease the development of a deep-learning approach for seismic velocity estimation, we have evaluated a simplified surrogate problem — the estimation of the root-mean-square (rms) and interval velocity in time from common-midpoint gathers — for 1D layered velocity models. We have developed a deep neural network, whose design was inspired by the information flow found in semblance analysis. The network replaces semblance estimation by a representation built with a deep convolutional neural network, and then it performs velocity estimation automatically with recurrent neural networks. The network is trained with synthetic data to identify primary reflection events, rms velocity, and interval velocity. For a synthetic test set containing 1D layered models, we find that rms and interval velocity are accurately estimated, with an error of less than [Formula: see text] for the rms velocity. We apply the neural network to a real 2D marine survey and obtain accurate rms velocity predictions leading to a coherent stacked section, in addition to an estimation of the interval velocity that reproduces the main structures in the stacked section. Our results provide strong evidence that neural networks can estimate velocity from seismic data and that good performance can be achieved on real data even if the training is based on synthetics. The findings for the 1D problem suggest that deep convolutional encoders and recurrent neural networks are promising components of more complex networks that can perform 2D and 3D velocity model building.
46
Li, Haoliang, Shiqi Wang e AlexC Kot. "Image Recapture Detection with Convolutional and Recurrent Neural Networks". Electronic Imaging 2017, n. 7 (29 gennaio 2017): 87–91. http://dx.doi.org/10.2352/issn.2470-1173.2017.7.mwsf-329.
47
Shang, Jin, e Mingxuan Sun. "Geometric Hawkes Processes with Graph Convolutional Recurrent Neural Networks". Proceedings of the AAAI Conference on Artificial Intelligence 33 (17 luglio 2019): 4878–85. http://dx.doi.org/10.1609/aaai.v33i01.33014878.
Abstract (sommario):
Hawkes processes are popular for modeling correlated temporal sequences that exhibit mutual-excitation properties. Existing approaches such as feature-enriched processes or variations of Multivariate Hawkes processes either fail to describe the exact mutual influence between sequences or become computational inhibitive in most real-world applications involving large dimensions. Incorporating additional geometric structure in the form of graphs into Hawkes processes is an effective and efficient way for improving model prediction accuracy. In this paper, we propose the Geometric Hawkes Process (GHP) model to better correlate individual processes, by integrating Hawkes processes and a graph convolutional recurrent neural network. The deep network structure is computational efficient since it requires constant parameters that are independent of the graph size. The experiment results on real-world data show that our framework outperforms recent state-of-art methods.
48
Qin, Chen, Jo Schlemper, Jose Caballero, Anthony N. Price, Joseph V. Hajnal e Daniel Rueckert. "Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction". IEEE Transactions on Medical Imaging 38, n. 1 (gennaio 2019): 280–90. http://dx.doi.org/10.1109/tmi.2018.2863670.
49
Zuo, Zhen, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, Bing Wang e Yushi Chen. "Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks". IEEE Transactions on Image Processing 25, n. 7 (luglio 2016): 2983–96. http://dx.doi.org/10.1109/tip.2016.2548241.
50
Cakir, Emre, Giambattista Parascandolo, Toni Heittola, Heikki Huttunen e Tuomas Virtanen. "Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection". IEEE/ACM Transactions on Audio, Speech, and Language Processing 25, n. 6 (giugno 2017): 1291–303. http://dx.doi.org/10.1109/taslp.2017.2690575.